参考官方历程即可：TensorFlow Lite Metadata Writer API

可能需要vpn打开。

官方例程分为了很多部分：

每部分解决方式不一样，找到自己对应的版本即可，我是Object detectors:

首先在环境下安装：

(base) C:\Users\Administrator>pip install tflite-support-nightly

 然后利用下面代码：

from tflite_support.metadata_writers import image_classifier
from tflite_support.metadata_writers import writer_utils

from tflite_support.metadata_writers import object_detector
from tflite_support.metadata_writers import writer_utils

ObjectDetectorWriter = object_detector.MetadataWriter
_MODEL_PATH = "E:/aa/2/android/app\src/main/assets/model_tflite.tflite"
# Task Library expects label files that are in the same format as the one below.
_LABEL_FILE = "E:/aa/2/android/app\src/main/assets/label.txt"
_SAVE_TO_PATH = "E:/aa/2/android/app\src/main/assets/model_tflite_meta.tflite"
# Normalization parameters is required when reprocessing the image. It is
# optional if the image pixel values are in range of [0, 255] and the input
# tensor is quantized to uint8. See the introduction for normalization and
# quantization parameters below for more details.
# https://www.tensorflow.org/lite/convert/metadata#normalization_and_quantization_parameters)
_INPUT_NORM_MEAN = 127.5
_INPUT_NORM_STD = 127.5

# Create the metadata writer.
writer = ObjectDetectorWriter.create_for_inference(
    writer_utils.load_file(_MODEL_PATH), [_INPUT_NORM_MEAN], [_INPUT_NORM_STD],
    [_LABEL_FILE])

# Verify the metadata generated by metadata writer.
print(writer.get_metadata_json())

# Populate the metadata into the model.
writer_utils.save_file(writer.populate(), _SAVE_TO_PATH)

只需要将下述代码代码修改自己文件对应（我是自己模型的.tflite）：

结果如下，即成功：

 回到

android打开文件：